archy/docker/routstr/archy-start.py

"""Start Routstr, then make the node's choices win over its saved settings.

Routstr seeds settings from the environment on first start only; afterwards
its database copy wins. The node wallet owns the mints and payout address
(CASHU_MINTS, RECEIVE_LN_ADDRESS, rendered by the orchestrator from the node
wallet), so they are re-applied through the admin API on every start. The model
entry's context is re-stated on every start, so buyers see the context size
llama-server really has. Its name, answer limit, price and on/off choice belong
to the operator (Settings, "What you sell"): they are set at install defaults
only when there is no entry yet, and priced only while unpriced (Routstr refuses
to serve an unpriced model).

Failures here are logged and never stop Routstr: unconfigured, it serves no
paid inference rather than the wrong mint.
"""

import json
import os
import signal
import subprocess
import sys
import time
import urllib.error
import urllib.request

API = "http://127.0.0.1:8000"
UVICORN = [
    "/opt/routstr/.venv/bin/python", "-m", "uvicorn", "routstr:fastapi_app",
    "--host", "0.0.0.0", "--port", "8000", "--no-access-log",
]


def log(message):
    print(f"archy-start: {message}", file=sys.stderr, flush=True)


def call(method, path, body=None, token=None):
    headers = {"Content-Type": "application/json"}
    if token:
        headers["Authorization"] = f"Bearer {token}"
    data = json.dumps(body).encode() if body is not None else None
    request = urllib.request.Request(API + path, data, headers, method=method)
    with urllib.request.urlopen(request, timeout=30) as response:
        return json.loads(response.read() or b"null")


def wait_ready(child, deadline):
    while time.monotonic() < deadline and child.poll() is None:
        try:
            call("GET", "/v1/info")
            return True
        except (urllib.error.URLError, OSError, ValueError):
            time.sleep(2)
    return False


def sync_settings(token):
    update = {}
    mints = [m.strip() for m in os.environ.get("CASHU_MINTS", "").split(",") if m.strip()]
    if mints:
        update["cashu_mints"] = mints
        update["primary_mint"] = mints[0]
    address = os.environ.get("RECEIVE_LN_ADDRESS", "").strip()
    if address:
        update["receive_ln_address"] = address
    if update:
        call("PATCH", "/admin/api/settings", update, token)
        log(f"applied node wallet settings: {sorted(update)}")


def priced(model):
    pricing = model.get("pricing") or {}
    return any(float(pricing.get(k) or 0) > 0 for k in ("prompt", "completion", "request"))


def sync_model(token):
    model_id = os.environ.get("ARCHY_MODEL_ID", "").strip()
    if not model_id:
        return
    path = f"/admin/api/upstream-providers/custom/models/{model_id}"
    try:
        existing = call("GET", path, token=token)
    except urllib.error.HTTPError as error:
        if error.code != 404:
            raise
        existing = None
    keep = existing if existing and priced(existing) else None
    pricing = keep["pricing"] if keep else {
        "prompt": os.environ["ARCHY_DEFAULT_PROMPT_USD_PER_TOKEN"],
        "completion": os.environ["ARCHY_DEFAULT_COMPLETION_USD_PER_TOKEN"],
        "request": "0", "image": "0", "web_search": "0", "internal_reasoning": "0",
    }
    context = int(os.environ.get("ARCHY_MODEL_CONTEXT", "4096"))
    max_completion = int(os.environ.get("ARCHY_MODEL_MAX_COMPLETION", "1024"))
    name = os.environ.get("ARCHY_MODEL_NAME", model_id)
    if existing:
        name = existing.get("name") or name
        kept = (existing.get("top_provider") or {}).get("max_completion_tokens")
        if isinstance(kept, int) and kept > 0:
            max_completion = kept
    max_completion = min(max_completion, context)
    call("POST", "/admin/api/upstream-providers/custom/models", {
        "id": model_id,
        "name": name,
        "description": "Local llama-server model",
        "created": 0,
        "context_length": context,
        "architecture": {
            "modality": "text->text", "input_modalities": ["text"],
            "output_modalities": ["text"], "tokenizer": "Other", "instruct_type": None,
        },
        "pricing": pricing,
        "top_provider": {
            "context_length": context, "max_completion_tokens": max_completion,
            "is_moderated": False,
        },
        "enabled": keep.get("enabled", True) if keep else True,
    }, token)
    log(f"{model_id}: context {context}, " + ("operator price kept" if keep else "priced at install defaults"))


def configure(child):
    if not wait_ready(child, time.monotonic() + 300):
        log("Routstr did not become ready; node settings not applied")
        return
    try:
        password = os.environ["ADMIN_PASSWORD"]
        token = call("POST", "/admin/api/login", {"password": password})["token"]
        sync_settings(token)
        sync_model(token)
    except Exception as error:  # never take Routstr down over configuration
        log(f"configuration failed ({type(error).__name__}): {error}")


def main():
    child = subprocess.Popen(UVICORN)
    stopping = []

    def forward(signum, _frame):
        stopping.append(signum)
        child.send_signal(signum)

    for sig in (signal.SIGTERM, signal.SIGINT):
        signal.signal(sig, forward)
    configure(child)
    code = child.wait()
    # uvicorn re-raises the stop signal after a graceful shutdown; a stop we
    # were asked for is a clean exit, not a crash for the orchestrator.
    if code < 0 and -code in stopping:
        code = 0
    sys.exit(code if code >= 0 else 128 - code)


if __name__ == "__main__":
    main()